ailocalinference

← All hardware

Tenstorrent Wormhole n300

Add-in card · immature software stack

OtherAdd-in GPU$1,400 · Aug 31, 2026Buy from Tenstorrent

Memory
24 GB~22 GB usable
Bandwidth
576GB/s — sets decode speed
Compute
60FP16 TFLOPS — sets prefill
Power
300 Wunder sustained load
Noise
50 dBAyou will hear it
Price per GB
$58of accelerator memory

Price history

tracking

Tracking since 2026-08-31 — not enough history for a trend yet.

1 observation recorded · Last checked 2026-08-31. Check the retailer before acting on this — we would rather say the data is old than pretend otherwise.

What it can run

2 of 6 reference workloads fit. The largest is 32B dense · Q4 (coding), at an estimated 20 tok/s of single-stream decode — #10 of the 17 machines here that can run it.

WorkloadNeedsFitsPrefill t/sDecode t/sBatched t/s$ per t/s
8B dense · Q4 (chat, drafts)
dense · 4.7 GB read per token
5.4 GBYes37580257$18
32B dense · Q4 (coding)
dense · 19 GB read per token
21.8 GBYes942064$70
70B dense · Q4 (strong general)
dense · 40 GB read per token
46 GBNo43929—
120B MoE A5B · MXFP4 (gpt-oss class)
MoE · 2.9 GB read per token
72.4 GBNo58883386—
320B MoE A18B · FP8 (frontier-ish)
MoE · 18 GB read per token
368 GBNo1671368—
671B MoE A37B · Q4 (DeepSeek class)
MoE · 18.5 GB read per token
437 GBNo811354—

Figures are modelled from this machine's bandwidth and compute, not measured on one. How they are derived →

Alternatives that also run 32B dense · Q4 (coding)

MachinePriceMemoryDecode t/s$ per t/s
$65024 GB16$41
$1,46024 GB33$44
Tenstorrent Wormhole n300 — this machine
$1,40024 GB20$70
$4,40032 GB61$72
$1,70032 GB22$77
$1,39932 GB18$78
$1,30032 GB16$81
$3,49924 GB34$103
$3,89948 GB30$130
$4,500128 GB21$214
$2,19948 GB9$244
$2,76064 GB11$251
$15,49996 GB61$254
$13,500512 GB41$329
$9,499512 GB28$339
$3,999128 GB9$444
$5,199128 GB9$578